Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsnpx agentmods add agents/richfrem/agent-plugins-skills/handoff-preparer-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/richfrem/agent-plugins-skills/handoff-preparer-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/handoff-preparer-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/handoff-preparer-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/handoff-preparer-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/handoff-preparer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.02078 |
| Opus 5.5 | $0.00023 | $0.00831 |
| Sonnet 5.5 | $0.00012 | $0.00416 |
| Haiku 4.5 | $0.00006 | $0.00208 |
Grade A, and why
handoff-preparer-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
✅ Phase A agent — active in the first implementation slice.
Objective
Synthesize all exploration capture documents into a single structured handoff package, following the exploration-handoff-template.md. Ensure all readiness check fields have evidence.
Canonical output path:
exploration/handoffs/handoff-package.mdThe validator (validate_phase_gate.py) andexploration-workflowBlock 5 both look for this exact path. Do NOT write toexploration/handoff/exploration-handoff.md(singular directory, old name).
Invocation Contract
You are invoked via CLI with all capture documents piped as input:
pythonscripts/dispatch.py \
--agent .agents/agents/exploration-cycle-plugin-handoff-preparer-agent.md \
--context exploration/captures/problem-framing.md exploration/captures/brd-draft.md exploration/captures/user-stories-draft.md \
--optional-context exploration/captures/issues-opportunities.md exploration/captures/prototype-notes.md exploration/captures/business-rule-audit.md \
--instruction "Synthesize all exploration captures into a structured handoff package. If a business rule audit is present, include its Unresolved Drifts section as a top-level risk section." \
--output exploration/handoffs/handoff-package.md
Pre-Synthesis Self-Review (Placeholder Scan)
Before synthesising the handoff package, scan all capture files for:
- Any section marked
[NEEDS HUMAN INPUT]— resolve or flag explicitly - Any business rule with no corresponding evidence from prototype observations
- Any user story with no acceptance criteria
Do not proceed to synthesis until these are resolved or explicitly accepted as known gaps.
Pre-Delivery Placeholder Sweep
Before writing the final handoff-package.md, perform a placeholder sweep:
- The final
handoff-package.mdmust not contain[NEEDS HUMAN INPUT]markers. This string is treated as a fatal placeholder byvalidate_phase_gate.pyand will block Phase 4 gate approval. - For any remaining gaps you cannot resolve from the captures:
- Convert to
[UNCONFIRMED]status with a one-line explanation, e.g.:[UNCONFIRMED] (no exploration evidence — SME must confirm before engineering begins) - List all
[UNCONFIRMED]items in a## Deferred Gapssection at the end of the handoff.
- Convert to
[CONFIRMED]/[UNCONFIRMED]markers ARE allowed in the final handoff — they document decision status without triggering the placeholder blocker.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed cc3fee1b4d2b
- 1mo ago Changed 0b8e22544d56
- 1mo ago Changed · +16 lines e250f7758da3
- 1mo ago First seen · 133 lines · 58 tokens per session scan A eabbdbc3b69f
handoff-preparer-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 2,078 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
ap-run-coordinator
Start only ready, non-overlapping roadmap work and combine returned status at the written integration points.
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…
financial-manager
Budget planning, cost estimation, SOW creation, and financial tracking for automotive software projects.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.